huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/eminem")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/m1jtunaa/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/3ewsu9zf/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
 
 ## Training procedure
 
 The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Eminem's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/2xezqr9j) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/228hhsot) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/2xezqr9j/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/228hhsot/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -18,7 +18,9 @@
   "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
   "scale_attn_weights": true,
   "summary_activation": null,
   "summary_first_dropout": 0.1,
@@ -35,7 +37,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.11.3",
+  "transformers_version": "4.12.0",
   "use_cache": true,
   "vocab_size": 50257
 }

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 0.6717901825904846, "eval_runtime": 32.3581, "eval_samples_per_second": 21.077, "eval_steps_per_second": 2.658, "epoch": 3.0}
+{"eval_loss": 0.536793053150177, "eval_runtime": 27.8473, "eval_samples_per_second": 22.444, "eval_steps_per_second": 2.837, "epoch": 4.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e4996cc5b01b2f5df2097ea186a2e86f7ee3597d536c4f655a2fc46fe7ba2cc
+oid sha256:8c4f87ab1eff90581e85a0e1a8b66c8bbdc05aa0f140d00508d68ab79ec62ebb
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71a25a4b42966c35fad23512f0a00af907488f398f69579bbf6993f208f7875f
+oid sha256:2736ac8126eeb3acab31bdda96c21bb571e1ee17ea73a22dac8507b663c7b97f
 size 995604017

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9621b75ec1fc38e7c917e2fcc638921268a3d38f2762a4ff89a10975fc0830c
+oid sha256:77194dc46668d0004843bde209b7980f1e28bafa5d4996a99526b9a6bf1206f3
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81db186b04d47e780c47c135689736ec200f7e269a91591d61577bc87d72dc42
+oid sha256:2403905a22d6fba3820922efb35175b8d0fee26b7667687784f25f62cc49001c
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0d0227464d22267541364a30983be6a0f32a9f218c9367e12431d626c7660eb
+oid sha256:9134467a4fb57c206ad7804754df5fb2c2150ce97742085a7f92d7d6b8fdc6f5
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.6717901825904846,
-  "best_model_checkpoint": "output/eminem/checkpoint-1350",
+  "best_metric": 0.536793053150177,
+  "best_model_checkpoint": "output/eminem/checkpoint-1371",
   "epoch": 3.0,
-  "global_step": 1350,
+  "global_step": 1371,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1650,11 +1650,43 @@
       "eval_samples_per_second": 21.1,
       "eval_steps_per_second": 2.661,
       "step": 1350
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 0.0001141037890981026,
+      "loss": 0.9662,
+      "step": 1355
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 0.00011584107440876515,
+      "loss": 0.9781,
+      "step": 1360
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 0.00011752255327383569,
+      "loss": 1.0047,
+      "step": 1365
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.00011914623934224141,
+      "loss": 1.0306,
+      "step": 1370
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.536793053150177,
+      "eval_runtime": 27.1721,
+      "eval_samples_per_second": 23.002,
+      "eval_steps_per_second": 2.907,
+      "step": 1371
     }
   ],
-  "max_steps": 1350,
-  "num_train_epochs": 3,
-  "total_flos": 1410062450688000.0,
+  "max_steps": 1828,
+  "num_train_epochs": 4,
+  "total_flos": 1431619043328000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad2c17509308df0501daa22f7c38deda6ee50f01e56c9f0747a3c0dbf3f69a2e
+oid sha256:19bbcaf668a94fe1eb5daa14962dff75a0d4631ce679cba94b96ee9567a54ad0
 size 2863